© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10086
    Prev
    Next
    INDEX
    Explanations

    tied to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    -3.42
     .
    -3.17
    en
    -3.09
    e
    -2.92
    J
    -2.89
     s
    -2.86
     z
    -2.84
    er
    -2.81
    l
    -2.78
     c
    -2.75
    POSITIVE LOGITS
    淠
    3.25
     öffnungszeiten
    3.02
     estrena
    2.98
     anunció
    2.95
    緜
    2.88
     versie
    2.83
    靦
    2.83
    嫑
    2.78
    鐿
    2.75
    ～、
    2.72
    Activations Density 0.003%

    No Known Activations